© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3383
    Prev
    Next
    INDEX
    Explanations

    elements related to governance and political authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.04
    3:0.07
    4:0.04
    5:0.07
    6:0.05
    7:0.04
    8:0.09
    9:0.07
    10:0.11
    11:0.34
    Negative Logits
     Citiz
    -1.99
     decriminal
    -1.91
    Oil
    -1.88
    LIB
    -1.88
    ernels
    -1.84
    ++++++++
    -1.80
     citiz
    -1.70
     commer
    -1.68
     boutique
    -1.67
    itutional
    -1.66
    POSITIVE LOGITS
    nown
    2.00
    iasm
    1.97
    hap
    1.94
    eric
    1.82
    oldown
    1.80
     Bach
    1.80
    ername
    1.79
    phe
    1.79
    elong
    1.78
    ],"
    1.77
    Activations Density 0.001%

    No Known Activations